arXiv AI
Aug 5
Autoreflection: How Agentic Strange Loops Turn Human Culture into AI Infrastructure
arXiv:2608. 03800v1 Announce Type: cross Abstract: An LLM-based agent is a loop that reads itself.
Copying explains the collective behavior of AI agents in the wild
Related stories
Hugging Face Trending Papers
Aug 4
Autoreflection: How Agentic Strange Loops Turn Human Culture into AI Infrastructure
An LLM-based agent is a loop that reads itself. Agentic frameworks externalize identity, memory, and disposition into editable files.
arXiv AI
Aug 18
When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding
arXiv:2608. 16801v1 Announce Type: new Abstract: We study how teams of AI coding agents coordinate while solving programming tasks.
arXiv AI
Jul 14
Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Stateful Personal Agents
arXiv:2607. 10526v1 Announce Type: new Abstract: Stateful personal agents increasingly maintain long-term user profiles, episodic memories, and reusable skills.
arXiv AI
Jun 19
Before the Pull Request: Mining Multi-Agent Coordination
arXiv:2606. 19616v1 Announce Type: cross Abstract: Autonomous coding agents now open millions of pull requests, yet large-scale studies find their PRs are produced faster but accepted less often - a coordination and trust gap that pull-request-level telemetry cannot explain.
arXiv Computation and Language
Sep 18
Message capacity and claim wording set the transition points of collective truth-finding in language-model networks
The study investigates how limited reading capacity and claim wording influence consensus outcomes in language‑model networks. By modeling message capacity as the number of messages an agent reads, the authors show that when agents read fewer than about 6.4 messages on average, a wrong consensus becomes unreachable. However, the wording of a claim—its inherent threshold—can override this effect, leading to incorrect consensus even when most agents start correct.
arXiv AI
Sep 4
Transfiver: Human-AI Co-Inference through a Shared Editable State
arXiv:2609. 03797v1 Announce Type: new Abstract: Long-term human-AI interaction is difficult because the information that guides inference is updated implicitly by the model and is not directly inspectable or controllable by the user.
arXiv AI
Sep 3
SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams
SkillGLoW introduces a new way for large language model agents to self‑improve by consolidating procedural skills shared across related tasks. Instead of storing all skills in a single global document or a flat per‑task pool, SkillGLoW aggregates local skills into procedural families, compresses them into de‑instantiated global priors, and regenerates instance‑specific details on demand. Experiments on four diverse benchmarks show that these priors improve performance by an average of 17.2 points over a no‑skill baseline, are more compact than per‑task pools, and enable better transfer to unseen tasks.
arXiv Computation and Language
Aug 31
Benchmarking large language model agent societies against human behavioural distributions
The paper introduces SILICA, an open instrument designed to evaluate whether large language model (LLM) agent societies replicate human behavioural distributions. Using five environments with human‑anchored data and perturbations, the study finds that most LLMs only match human behaviour at initial stages, failing to reproduce end‑state cooperation or correct acceptance thresholds. The results suggest that current LLM societies can support exploratory claims but do not yet reliably emulate human social dynamics.
arXiv AI
Sep 24
How a shared state is described determines whether AI agents synchronize
The article investigates how the textual description of a shared state influences the collective behavior of language‑model agents. By testing 507,112 responses across different model families on a circular coordination task, the authors show that varying the state description (e.g., numerical summaries vs. histograms) can alter whether agents align, split, or fail to coordinate. The study demonstrates that the way a shared state is described is an integral part of the interaction rule that determines collective order.
arXiv AI
3d ago
From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs
arXiv:2609.38516v1 Announce Type: cross Abstract: Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to wor...
arXiv AI
3d ago
The Backdrop Exposes What the World Around an Agent Costs It
The paper introduces BACKDROP, a benchmark that evaluates how well AI agents maintain their capabilities when faced with everyday hazards in dynamic environments. BACKDROP adds four types of hazards—authority, injection, boundary, and fault—to a task’s execution environment and measures whether agents can still achieve the correct end state. Across 3,678 variants and 16 models, the average success rate drops dramatically from 69.5% to 31.3% when all hazards are present, revealing that agents often follow unauthorized requests and fail to resist injected text.